Heinrich von Busch
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Heinrich von Busch has a total of 76 co-authors. Here are the top co-authors by number of shared publications:
- Robert Grimm
Siemens Healthineers AG, Erlangen, Germany
8 shared publications - Ali Kamen
Digital Technology and Innovation, Siemens Healthineers, Princeton, USA
5 shared publications - Bin Lou
Digital Technology and Innovation, Siemens Healthineers, Princeton, NJ
5 shared publications - Hans Meine
Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
4 shared publications - Markus Wenzel
Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
4 shared publications - Moon Hyung Choi
Department of Radiology, Eunpyeong St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea
4 shared publications
Latest Publications
- 1 October 2026
- Published by Springer Nature
- p. 191-209
From Minimal Clinical Prompts to 3D: Spacing-Aware Prompt Propagation for Multimodal Prostate Lesion Segmentation in bpMRI
- 1 October 2026
- Published by Springer Nature
- p. 191-209
From Minimal Clinical Prompts to 3D: Spacing-Aware Prompt Propagation for Multimodal Prostate Lesion Segmentation in bpMRI
- Open Access
- 1 September 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (05) , 1-18
Multi-institutional classification of lesions in breast MRI: a comparison of one-stage and two-stage methods
PurposeBreast magnetic resonance imaging (MRI) is widely used for diagnostic imaging in breast cancer, creating a need for automated image analysis to assist early detection and diagnosis. We approach the task of lesion suspiciousness classification in breast MRI.ApproachUsing a multi-centric data collection of 3792 patients, we compare a two-stage classification model based on nnU-Net and a three-dimensional (3D) Swin Transformer with the one-stage classifiers nnDetection and RadYOLO, our 3D extension of YOLO11.ResultsIn a fivefold leave-sites-out cross-validation scheme, the mean (standard deviation) across folds of the lesion classification area under the receiver operating curve (ROC-AUC) is 0.754 (0.086) for the two-stage model, 0.693 (0.108) for nnDetection, 0.737 (0.074) for RadYOLO, and 0.755 (0.064) for RadYOLO with a separate classification output.ConclusionsAlthough classification performance does not differ conclusively across methods, RadYOLO achieves 3 to 10 times shorter inference times.
- 1 September 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (05) , 1-18
Open AccessMulti-institutional classification of lesions in breast MRI: a comparison of one-stage and two-stage methods
PurposeBreast magnetic resonance imaging (MRI) is widely used for diagnostic imaging in breast cancer, creating a need for automated image analysis to assist early detection and diagnosis. We approach the task of lesion suspiciousness classification in breast MRI.ApproachUsing a multi-centric data collection of 3792 patients, we compare a two-stage classification model based on nnU-Net and a three-dimensional (3D) Swin Transformer with the one-stage classifiers nnDetection and RadYOLO, our 3D extension of YOLO11.ResultsIn a fivefold leave-sites-out cross-validation scheme, the mean (standard deviation) across folds of the lesion classification area under the receiver operating curve (ROC-AUC) is 0.754 (0.086) for the two-stage model, 0.693 (0.108) for nnDetection, 0.737 (0.074) for RadYOLO, and 0.755 (0.064) for RadYOLO with a separate classification output.ConclusionsAlthough classification performance does not differ conclusively across methods, RadYOLO achieves 3 to 10 times shorter inference times.
- Open Access
- 1 May 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (03) , 1-16
Multi-institutional classification of fibroglandular tissue and background parenchymal enhancement in breast MRI using deep learning
PurposeThe amount of fibroglandular tissue (FGT) and background parenchymal enhancement (BPE) are evaluated as part of the BI-RADS reporting standard for the diagnosis of breast cancer in magnetic resonance imaging (MRI). BPE is associated with breast cancer risk and affects the diagnostic accuracy of breast MRI readings but is subject to very high inter-reader variability.ApproachWe developed a fully automatic observer-independent method to measure the amount of FGT and BPE based on breast, FGT, and lesion masks, which classifies each into four classes based on thresholds applied to those scores. This retrospective study involved 2840 patients from seven institutions for whom T1-weighted dynamic contrast-enhanced breast MRI sequences with and without fat suppression were acquired using 1.5 or 3T scanners. FGT and BPE assessments for model development and evaluation were performed according to the BI-RADS guidelines by radiologists from the respective institutions and by a radiographer if the assessments were missing.ResultsThe performance of the models was compared using four-class accuracy and a paired t-test (α=0.05). Our automatic classification of FGT and BPE in a multi-institutional setting achieved a four-class accuracy of 0.535 for FGT and 0.504 for BPE (random=0.25). The calibration of the classification thresholds for each site individually resulted in a significant improvement, reaching an accuracy of 0.669 (p<0.05) for FGT and 0.565 (p<0.05) for BPE. The area under curve of receiver operating characterstic (ROC-AUC) to classify FGT and BPE into low versus high is 0.883 for FGT and 0.757 for BPE when computed across all sites. The averaged per-site AUCs are 0.926 for FGT and 0.810 for BPE.ConclusionFGT and BPE classification perform significantly better when classification thresholds are selected per clinical site.
- 1 May 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (03) , 1-16
Open AccessMulti-institutional classification of fibroglandular tissue and background parenchymal enhancement in breast MRI using deep learning
PurposeThe amount of fibroglandular tissue (FGT) and background parenchymal enhancement (BPE) are evaluated as part of the BI-RADS reporting standard for the diagnosis of breast cancer in magnetic resonance imaging (MRI). BPE is associated with breast cancer risk and affects the diagnostic accuracy of breast MRI readings but is subject to very high inter-reader variability.ApproachWe developed a fully automatic observer-independent method to measure the amount of FGT and BPE based on breast, FGT, and lesion masks, which classifies each into four classes based on thresholds applied to those scores. This retrospective study involved 2840 patients from seven institutions for whom T1-weighted dynamic contrast-enhanced breast MRI sequences with and without fat suppression were acquired using 1.5 or 3T scanners. FGT and BPE assessments for model development and evaluation were performed according to the BI-RADS guidelines by radiologists from the respective institutions and by a radiographer if the assessments were missing.ResultsThe performance of the models was compared using four-class accuracy and a paired t-test (α=0.05). Our automatic classification of FGT and BPE in a multi-institutional setting achieved a four-class accuracy of 0.535 for FGT and 0.504 for BPE (random=0.25). The calibration of the classification thresholds for each site individually resulted in a significant improvement, reaching an accuracy of 0.669 (p<0.05) for FGT and 0.565 (p<0.05) for BPE. The area under curve of receiver operating characterstic (ROC-AUC) to classify FGT and BPE into low versus high is 0.883 for FGT and 0.757 for BPE when computed across all sites. The averaged per-site AUCs are 0.926 for FGT and 0.810 for BPE.ConclusionFGT and BPE classification perform significantly better when classification thresholds are selected per clinical site.
- 12 March 2026
- Published by Springer Nature
- p. 277-284
Applying Active Learning to Nipple Segmentation in Breast MRI
- 12 March 2026
- Published by Springer Nature
- p. 277-284
Applying Active Learning to Nipple Segmentation in Breast MRI
- Top Cited Papers
- 1 March 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 314 (3) , e232788
MRI-based Deep Learning Algorithm for Assisting Clinically Significant Prostate Cancer Detection: A Bicenter Prospective Study
A commercial MRI-based deep learning algorithm for prostate cancer detection showed greater positive predictive value, despite its lower sensitivity, potentially allowing it to assist radiologists in biopsy planning.
- 1 March 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 314 (3) , e232788
Top Cited PapersMRI-based Deep Learning Algorithm for Assisting Clinically Significant Prostate Cancer Detection: A Bicenter Prospective Study
A commercial MRI-based deep learning algorithm for prostate cancer detection showed greater positive predictive value, despite its lower sensitivity, potentially allowing it to assist radiologists in biopsy planning.
- Open Access
Multi-Center Benchmarking of a Commercially Available Artificial Intelligence Algorithm for Prostate Imaging Reporting and Data System (PI-RADS) Score Assignment and Lesion Detection in Prostate MRI
Background: The increase in multiparametric magnetic resonance imaging (mpMRI) examinations as a fundamental tool in prostate cancer (PCa) diagnostics raises the need for supportive computer-aided imaging analysis. Therefore, we evaluated the performance of a commercially available AI-based algorithm for prostate cancer detection and classification in a multi-center setting. Methods: Representative patients with 3T mpMRI between 2017 and 2022 at three different university hospitals were selected. Exams were read according to the PI-RADSv2.1 protocol and then assessed by an AI algorithm. Diagnostic accuracy for PCa of both human and AI readings were calculated using MR-guided ultrasound fusion biopsy as the gold standard. Results: Analysis of 91 patients resulted in 138 target lesions. Median patient age was 67 years (range: 49–82), median PSA at the time of the MRI exam was 8.4 ng/mL (range: 1.47–73.7). Sensitivity and specificity for clinically significant prostate cancer (csPCa, defined as ISUP ≥ 2) were 92%/64% for radiologists vs. 91%/57% for AI detection on patient level and 90%/70% vs. 81%/78% on lesion level, respectively (cut-off PI-RADS ≥ 4). Two cases of csPCa were missed by the AI on patient-level, resulting in a negative predictive value (NPV) of 0.88 at a cut-off of PI-RADS ≥ 3. Conclusions: AI-augmented lesion detection and scoring proved to be a robust tool in a multi-center setting with sensitivity comparable to the radiologists, even outperforming human reader specificity on both patient and lesion levels at a threshold of PI-RADS ≥3 and a threshold of PI-RADS ≥ 4 on lesion level. In anticipation of refinements of the algorithm and upon further validation, AI-detection could be implemented in the clinical workflow prior to human reading to exclude PCa, thereby drastically improving reading efficiency.
Open AccessMulti-Center Benchmarking of a Commercially Available Artificial Intelligence Algorithm for Prostate Imaging Reporting and Data System (PI-RADS) Score Assignment and Lesion Detection in Prostate MRI
Background: The increase in multiparametric magnetic resonance imaging (mpMRI) examinations as a fundamental tool in prostate cancer (PCa) diagnostics raises the need for supportive computer-aided imaging analysis. Therefore, we evaluated the performance of a commercially available AI-based algorithm for prostate cancer detection and classification in a multi-center setting. Methods: Representative patients with 3T mpMRI between 2017 and 2022 at three different university hospitals were selected. Exams were read according to the PI-RADSv2.1 protocol and then assessed by an AI algorithm. Diagnostic accuracy for PCa of both human and AI readings were calculated using MR-guided ultrasound fusion biopsy as the gold standard. Results: Analysis of 91 patients resulted in 138 target lesions. Median patient age was 67 years (range: 49–82), median PSA at the time of the MRI exam was 8.4 ng/mL (range: 1.47–73.7). Sensitivity and specificity for clinically significant prostate cancer (csPCa, defined as ISUP ≥ 2) were 92%/64% for radiologists vs. 91%/57% for AI detection on patient level and 90%/70% vs. 81%/78% on lesion level, respectively (cut-off PI-RADS ≥ 4). Two cases of csPCa were missed by the AI on patient-level, resulting in a negative predictive value (NPV) of 0.88 at a cut-off of PI-RADS ≥ 3. Conclusions: AI-augmented lesion detection and scoring proved to be a robust tool in a multi-center setting with sensitivity comparable to the radiologists, even outperforming human reader specificity on both patient and lesion levels at a threshold of PI-RADS ≥3 and a threshold of PI-RADS ≥ 4 on lesion level. In anticipation of refinements of the algorithm and upon further validation, AI-detection could be implemented in the clinical workflow prior to human reading to exclude PCa, thereby drastically improving reading efficiency.
- 1 September 2024
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 6 (5) , e230521
Deep Learning–based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets
To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various b values, to align with the style of images acquired using b values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (P < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (P < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (P < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (P < .001) for lesions with PI-RADS scores of 4 or greater. UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various b values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high b value). Keywords: Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, b Value Supplemental material is available for this article. © RSNA, 2024
- 1 September 2024
- Published by Radiological Society of North America (RSNA) in Radiology: Artificial Intelligence
- Vol. 6 (5) , e230521
Deep Learning–based Unsupervised Domain Adaptation via a Unified Model for Prostate Lesion Detection Using Multisite Biparametric MRI Datasets
To determine whether the unsupervised domain adaptation (UDA) method with generated images improves the performance of a supervised learning (SL) model for prostate cancer (PCa) detection using multisite biparametric (bp) MRI datasets. This retrospective study included data from 5150 patients (14 191 samples) collected across nine different imaging centers. A novel UDA method using a unified generative model was developed for PCa detection using multisite bpMRI datasets. This method translates diffusion-weighted imaging (DWI) acquisitions, including apparent diffusion coefficient (ADC) and individual diffusion-weighted (DW) images acquired using various b values, to align with the style of images acquired using b values recommended by Prostate Imaging Reporting and Data System (PI-RADS) guidelines. The generated ADC and DW images replace the original images for PCa detection. An independent set of 1692 test cases (2393 samples) was used for evaluation. The area under the receiver operating characteristic curve (AUC) was used as the primary metric, and statistical analysis was performed via bootstrapping. For all test cases, the AUC values for baseline SL and UDA methods were 0.73 and 0.79 (P < .001), respectively, for PCa lesions with PI-RADS score of 3 or greater and 0.77 and 0.80 (P < .001) for lesions with PI-RADS scores of 4 or greater. In the 361 test cases under the most unfavorable image acquisition setting, the AUC values for baseline SL and UDA were 0.49 and 0.76 (P < .001) for lesions with PI-RADS scores of 3 or greater and 0.50 and 0.77 (P < .001) for lesions with PI-RADS scores of 4 or greater. UDA with generated images improved the performance of SL methods in PCa lesion detection across multisite datasets with various b values, especially for images acquired with significant deviations from the PI-RADS-recommended DWI protocol (eg, with an extremely high b value). Keywords: Prostate Cancer Detection, Multisite, Unsupervised Domain Adaptation, Diffusion-weighted Imaging, b Value Supplemental material is available for this article. © RSNA, 2024
- 20 February 2024
- Published by Springer Nature
- p. 178-183
Application of Active Learning-based on Uncertainty Quantification to Breast Segmentation in MRI
- 20 February 2024
- Published by Springer Nature
- p. 178-183
Application of Active Learning-based on Uncertainty Quantification to Breast Segmentation in MRI
- Open Access
- 1 January 2023
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 42 (1) , 154-164
Prostate gland volume estimation: anteroposterior diameters measured on axial versus sagittal ultrasonography and magnetic resonance images
Purpose: The aim of this study was to evaluate the accuracy of prostate volume estimates calculated from the ellipsoid formula using the anteroposterior (AP) diameter measured on axial and sagittal images obtained through ultrasonography (US) and magnetic resonance imaging (MRI).Methods: This retrospective study included 456 patients with transrectal US and MRI from two university hospitals. Two radiologists independently measured the prostate gland diameters on US and MRI: AP diameters on axial and sagittal images, transverse, and longitudinal diameters on midsagittal images. The volume estimates, volumeax and volumesag, were calculated from the ellipsoid formula by using the AP diameter on axial and sagittal images, respectively. The prostate volume extracted from MRI-based whole-gland segmentation was considered the gold standard. The intraclass correlation coefficient (ICC) was used to evaluate the inter-method agreement between volumeax and volumesag, and agreement with the gold standard. The Wilcoxon signedrank test was used to analyze the differences between the volume estimates and the gold standard.Results: The prostate gland volume estimates showed excellent inter-method agreement, and excellent agreement with the gold standard (ICCs >0.9). Compared with the gold standard, the volume estimates were significantly larger on MRI and significantly smaller on US (P<0.001). The volume difference (segmented volume–volume estimate) was greater in patients with larger prostate glands, especially on US.Conclusion: Volumeax and volumesag showed excellent inter-method agreement and excellent agreement with the gold standard on both US and MRI. However, prostate volume was overestimated on MRI and underestimated on US.
- 1 January 2023
- Published by Korean Society of Ultrasound in Medicine in Ultrasonography
- Vol. 42 (1) , 154-164
Open AccessProstate gland volume estimation: anteroposterior diameters measured on axial versus sagittal ultrasonography and magnetic resonance images
Purpose: The aim of this study was to evaluate the accuracy of prostate volume estimates calculated from the ellipsoid formula using the anteroposterior (AP) diameter measured on axial and sagittal images obtained through ultrasonography (US) and magnetic resonance imaging (MRI).Methods: This retrospective study included 456 patients with transrectal US and MRI from two university hospitals. Two radiologists independently measured the prostate gland diameters on US and MRI: AP diameters on axial and sagittal images, transverse, and longitudinal diameters on midsagittal images. The volume estimates, volumeax and volumesag, were calculated from the ellipsoid formula by using the AP diameter on axial and sagittal images, respectively. The prostate volume extracted from MRI-based whole-gland segmentation was considered the gold standard. The intraclass correlation coefficient (ICC) was used to evaluate the inter-method agreement between volumeax and volumesag, and agreement with the gold standard. The Wilcoxon signedrank test was used to analyze the differences between the volume estimates and the gold standard.Results: The prostate gland volume estimates showed excellent inter-method agreement, and excellent agreement with the gold standard (ICCs >0.9). Compared with the gold standard, the volume estimates were significantly larger on MRI and significantly smaller on US (P<0.001). The volume difference (segmented volume–volume estimate) was greater in patients with larger prostate glands, especially on US.Conclusion: Volumeax and volumesag showed excellent inter-method agreement and excellent agreement with the gold standard on both US and MRI. However, prostate volume was overestimated on MRI and underestimated on US.